Grammalecte  Check-in [45d2b648e6]

Overview
Comment:[core] gc_engine: some comments
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | rg
Files: files | file ages | folders
SHA3-256: 45d2b648e64049a2c2e38ff8194523a34f1734bb4c259c2967626b2e4f2dd82e
User & Date: olr on 2018-06-23 11:23:28
Other Links: branch diff | manifest | tags
Context
2018-06-23
11:24
[fr] notes sur la langue française + adaptation de règles concernant les pronoms check-in: 71f721941f user: olr tags: fr, rg
11:23
[core] gc_engine: some comments check-in: 45d2b648e6 user: olr tags: core, rg
08:11
[fr] conversion: regex rules -> graph rules check-in: c79567338a user: olr tags: fr, rg
Changes

Modified gc_core/py/lang_core/gc_engine.py from [dbd98c6fb9] to [3fb4a33065].

589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
589
590
591
592
593
594
595

596
597
598
599
600
601
602







-







        self.sSentence0 = sSentence0
        self.nOffsetWithinParagraph = nOffset
        self.lToken = list(_oTokenizer.genTokens(sSentence, True))
        self.dTokenPos = { dToken["nStart"]: dToken  for dToken in self.lToken }
        self.dTags = {}
        self.createError = self._createWriterError  if _bWriterError  else self._createDictError


    def update (self, sSentence):
        self.sSentence = sSentence
        self.lToken = list(_oTokenizer.genTokens(sSentence, True))

    def _getNextMatchingNodes (self, dToken, dGraph, dNode, bDebug=False):
        "generator: return nodes where <dToken> “values” match <dNode> arcs"
        # token value
671
672
673
674
675
676
677

678
679
680
681
682
683
684
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684







+







                        if not sPattern or any(re.search(sPattern, sMorph)  for sMorph in _oSpellChecker.getMorph(dToken["sValue"])):
                            if bDebug:
                                print("  MATCH: @" + sRegex)
                            yield dGraph[dNode["<re_morph>"][sRegex]]
        # meta arc (for token type)
        if "<meta>" in dNode:
            for sMeta in dNode["<meta>"]:
                # not regex here, we just search if <dNode["sType"]> exists within <sMeta>
                if sMeta == "*":
                    if bDebug:
                        print("  MATCH: *" + sMeta)
                    yield dGraph[dNode["<meta>"]["*"]]
                elif "¬" in sMeta:
                    if dNode["sType"] not in sMeta:
                        if bDebug:
730
731
732
733
734
735
736
737

738
739
740
741
742
743
744
730
731
732
733
734
735
736

737
738
739
740
741
742
743
744







-
+







                    if bDebug:
                        print("ACTION:", sRuleId)
                        print(dRule[sRuleId])
                    sOption, sFuncCond, cActionType, sWhat, *eAct = dRule[sRuleId]
                    # Suggestion    [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, nPriority, message, URL ]
                    # TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd ]
                    # Disambiguator [ option, condition, "=", replacement/suggestion/action ]
                    # Tag           [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ]
                    # Sentence Tag  [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ]
                    # Test          [ option, condition, ">", "" ]
                    if not sOption or dOptions.get(sOption, False):
                        bCondMemo = not sFuncCond or globals()[sFuncCond](self.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, self.dTags, self.sSentence, self.sSentence0)
                        if bCondMemo:
                            if cActionType == "-":
                                # grammar error
                                nTokenErrorStart = nTokenOffset + eAct[0]